Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    extra heartbeats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \]
    0.51
     Template
    0.46
    standing
    0.45
    <0x0D>
    0.44
    甶
    0.44
    ამო
    0.43
    捞
    0.42
    Another
    0.42
     Another
    0.41
     Rein
    0.41
    POSITIVE LOGITS
     racconta
    0.64
    🙀
    0.63
     thrives
    0.61
     satire
    0.61
    色彩
    0.61
     surpr
    0.61
    ড
    0.61
     embossed
    0.60
    apuris
    0.59
     অপর্ণ
    0.59
    Act Density 0.001%

    No Known Activations